About Me
I am a researcher in the Multimedia Standards Team at ByteDance's Multimedia Laboratory, where I work on learning-based image and video compression systems and their standardization.
I received my Ph.D. in Computer Science from Peking University in 2026, advised by Prof. Ronggang Wang, and my B.Eng. from Chongqing University in 2021.
Career
-
ByteDance
Researcher · Multimedia Standards
Jul 2026 – Present
-
ByteDance
Research Intern · Multimedia Standards
Feb 2023 – Jul 2026
-
SenseTime
Research Intern · ISP & Codec Group
Jan 2022 – Sep 2022
Education
-
Ph.D. in Computer Science
Peking University
Advisor: Prof. Ronggang Wang
Sep 2021 – Jun 2026
-
B.Eng. in Vehicle Engineering
Chongqing University
Sep 2017 – Jun 2021
Publications
Neural Video Compression
-
2026
BiCRVC: An Efficient Bidirectional Neural Video Compression Framework via Coupled Representation Coding
arXiv preprint arXiv:2608.16175, 2026 Preprint
Codes motion and frame latents through one coupled codec, with multi-candidate motion estimation and bidirectional motion feature propagation; about 30× faster 1080p decoding than recent bidirectional codecs.
-
2025
BiECVC: Gated Diversification of Bidirectional Contexts for Learned Video Compression
Proceedings of the 33rd ACM International Conference on Multimedia (ACM MM), 7248–7257, 2025 CCF-A
First end-to-end video codec to outperform VTM 13.2 RA across all test sets; 13.4% bitrate saving at intra period 32.
-
2025
ECVC: Exploiting Non-Local Correlations in Multiple Frames for Contextual Video Compression
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7331–7341, 2025 CCF-A
Linear-attention motion estimation that models redundancy without explicit optical flow; 32.1% bitrate saving over VTM 13.2 LDB.
-
2024
LVC-LGMC: Joint Local and Global Motion Compensation for Learned Video Compression
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2955–2959, 2024 Oral
Combines local and global motion compensation for low-delay learned video compression.
Neural Image Compression
-
2026
MLICv2: Enhanced Multi-Reference Entropy Modeling for Learned Image Compression
ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 22(4), 1–23, 2026 CCF-B
Enhanced transforms, context re-weighting, entropy-coding skip and online encoder optimization; 16.5–20.5% bitrate saving over VTM 17.0 Intra on Kodak.
-
2026
SSCL: Adversarially Guided Image Compression via Semantic and Spectral Consistency Learning
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 40(17), 14937–14945, 2026 CCF-AOral
Perceptual image compression guided by spectral and semantic consistency; 35.9% bitrate saving over the previous best perception-oriented method.
-
2025
-
2025
MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression
ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 21(5), 1–25, 2025 CCF-B
Linear-complexity global context modelling that replaces full attention at a fraction of the memory cost; 13.4% bitrate saving over VTM 17.0 Intra.
-
2024
LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression
IEEE Transactions on Multimedia (TMM), 26, 10937–10951, 2024 CCF-A
Dynamic large-kernel transforms that widen the receptive field of the analysis and synthesis networks; 10.9% bitrate saving over VTM 17.0 Intra.
-
2023
Image Quality Assessment
-
2022
Image Quality Assessment with Transformers and Multi-Metric Fusion Modules
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 1804–1808, 2022
A learned metric combining ConvNeXt features, transformer-based distortion comparison and multi-metric fusion; 0.780 accuracy on the CLIC validation set.
Awards
-
Runner-up, CLIC 2024 Image Track
Challenge on Learned Image Compression @ DCC 2024
2024
-
Third place, Practical End-to-End Image/Video Compression Challenge
Visual Communications and Image Processing (VCIP) 2023
2023
-
Runner-up, CLIC 2022 Image Track
Challenge on Learned Image Compression @ CVPR 2022
2022
Service
- Conference Reviewer
-
- Conference on Neural Information Processing Systems (NeurIPS) 2026
- International Conference on Machine Learning (ICML) 2025, 2026
- International Conference on Learning Representations (ICLR) 2025, 2026, 2027
- AAAI Conference on Artificial Intelligence (AAAI) 2026, 2027
- ACM International Conference on Multimedia (ACM MM) 2024, 2025
- ACM International Conference on Multimedia, Dataset Track (ACM MM) 2025
- Data Compression Conference (DCC) 2024
- Journal Reviewer
-
- IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
- IEEE Transactions on Image Processing (TIP)
- IEEE Transactions on Multimedia (TMM)
- IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
- IEEE Transactions on Industrial Informatics (TII)
- IEEE Transactions on Broadcasting (TB)
- ACM Transactions on Multimedia Computing, Communications and Applications (TOMM)
- Pattern Recognition (PR)
- Organization
-
- Grand Challenge on Neural Network-based Video Coding, IEEE International Symposium on Circuits and Systems (ISCAS) 2024, 2025